Skip to content

Benchmark

OpenAI COBOL migration · Exact behavior accuracy

Scores are percentages. Higher is better.

Models measured
2
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

63.3%
Mean
86.6%
Median
41.2%
Std dev
5.4%
10th percentile
97.9%
90th percentile
5.4%
Min
5.4%97.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-6.1 SolOpenAI publication · COBOL to C++/Java/Kotlin/Python/Rust · hidden byte-for-byte tests · reasoning: higher level, exact tier not stated · exact API snapshot and run count not stated· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.97.9%
2GPT-6.1 SolOpenAI publication · COBOL to C++/Java/Kotlin/Python/Rust · hidden byte-for-byte tests · reasoning: low · exact API snapshot and run count not stated· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.6%
3GPT-5.6 SolOpenAI publication · COBOL to C++/Java/Kotlin/Python/Rust · hidden byte-for-byte tests · reasoning: low · exact API snapshot and run count not stated· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.5.4%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.